© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11844
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of deficiencies and the concept of action related to health or wellness issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to verbs related to being, having, or existing (particularly "has", "would", "will", "was", "is", "be").

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.88
     propOrder
    -0.72
    contentLoaded
    -0.69
    :✨
    -0.68
     تضيفلها
    -0.68
     '\\;'
    -0.67
    parsedMessage
    -0.67
     pinulongan
    -0.67
     transfieras
    -0.66
    RegressionTest
    -0.66
    POSITIVE LOGITS
     means
    0.36
     risk
    0.34
     is
    0.33
     without
    0.32
     habit
    0.31
     by
    0.31
     depends
    0.31
     slower
    0.29
     deb
    0.29
     wise
    0.29
    Activations Density 0.500%

    No Known Activations